跳到正文
cccskills
免费在 GitHub 公开

setup-telegram

Check Telegram bot configuration and guide setup if anything is missing.

中文简介正在准备中。当前显示原文说明。

集成工具Telegram
查看安装方法

包含的文件(1)

  • SKILL.md3.3 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Setup Telegram

Check if the Telegram bot is properly configured by reading config files. Do NOT use Bash — use the Read tool only.

Files to check

Read each of these files and verify the required values:

  1. Read .env in the project root. Check for:

    • TELEGRAM_BOT_TOKEN — must exist and be non-empty
    • TELEGRAM_OWNER_ID — must exist (numeric Telegram user ID)
    • CHANNEL_AUTO_START — must be true
    • CHANNEL_PROJECT_ROOT — the absolute path to the project the daemon works with (e.g., C:\dev\projects\agent-studio). Task executors use this as their working directory for git, file, and code operations. If missing, defaults to the daemon's startup directory.
    • TELEGRAM_ALLOWED_USERS — recommended (comma-separated user IDs)
    • ANTHROPIC_API_KEY or CLAUDE_CODE_OAUTH_TOKEN — needed for headless monitor auth
  2. Read ~/.claude/channels/telegram/access.json (path: C:\Users\oimir\.claude\channels\telegram\access.json). Check for:

    • allowFrom array with at least one user ID
  3. Read ~/.claude/channels/telegram/.env (path: C:\Users\oimir\.claude\channels\telegram\.env). Check for:

    • TELEGRAM_BOT_TOKEN present
  4. Read .claude/.mcp.json. Check for:

    • telegram-relay key in mcpServers

Report format

Show a simple checklist:

Telegram Setup Status:
  [x] .env: Bot token configured
  [x] .env: Owner ID: 6521653928
  [x] .env: CHANNEL_AUTO_START=true
  [x] .env: CHANNEL_PROJECT_ROOT=C:\dev\projects\agent-studio
  [x] .env: Allowed users: 6521653928
  [x] .env: Auth token configured (API key or OAuth token)
  [x] Voice: transcribe-anything installed (pip)
  [x] MCP: telegram-relay registered
  [x] access.json: 1 allowed user
  [x] channels/.env: token present

For any [ ] items, tell the user exactly what to add and where.

If both ANTHROPIC_API_KEY and CLAUDE_CODE_OAUTH_TOKEN are missing, tell the user:

  • "The headless Telegram monitor needs auth credentials to run independently."
  • "Option 1: Run ! claude setup-token in your terminal, then add CLAUDE_CODE_OAUTH_TOKEN=<token> to .env"
  • "Option 2: Add ANTHROPIC_API_KEY=sk-ant-... to .env (get one from console.anthropic.com)"
  • "Without one of these, the monitor can't authenticate and will fail to start."

If everything passes: "All configured! Run /enable-telegram to start monitoring."

Voice message support (optional): If the user wants voice messages to be transcribed, they need:

  • pip install transcribe-anything — Whisper-based speech-to-text (required for voice)
  • ELEVENLABS_API_KEY or OPENAI_API_KEY in .env — for TTS audio responses (optional)
  • Without transcribe-anything, voice messages get a "please type instead" fallback

Important

  • Use ONLY the Read tool — do NOT use Bash, curl, or any external commands
  • Do NOT attempt to validate the token against the Telegram API
  • The router lockdown prevents Bash — this skill must work with Read only

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Ensure accessibility in UI components including semantic HTML, ARIA attributes, keyboard navigation, and WCAG 2.2 AA compliance.

中文简介正在准备中。当前显示原文说明。

oimiragieo/agent-studio422026年7月14日 更新

Use when you want to improve response quality through meta-cognitive reasoning. Applies 15+ reasoning methods to reconsider and refine initial outputs.

中文简介正在准备中。当前显示原文说明。

oimiragieo/agent-studio422026年7月14日 更新

N-round opposing-stance debates for trade-off analysis. Assigns pro/con roles to agents, runs structured debate rounds with quality scoring, and produces a moderator synthesis with confidence-rated recommendation. Generalizable to architecture, technology, security, and design decisions.

中文简介正在准备中。当前显示原文说明。

oimiragieo/agent-studio422026年7月14日 更新

Force adversarial code review stance that eliminates confirmation bias — reviewer must find issues or re-analyze

中文简介正在准备中。当前显示原文说明。

oimiragieo/agent-studio422026年7月14日 更新

Creates specialized AI agents on-demand when no existing agent matches a request. Use when the Router cannot find a suitable agent for a task. Enables self-evolution by generating persistent agents.

中文简介正在准备中。当前显示原文说明。

oimiragieo/agent-studio422026年7月14日 更新

LLM-as-judge evaluation framework with 5-dimension rubric (accuracy, groundedness, coherence, completeness, helpfulness) for scoring AI-generated content quality with weighted composite scores and evidence citations

中文简介正在准备中。当前显示原文说明。

oimiragieo/agent-studio422026年7月14日 更新

查看 oimiragieo 的全部技能

报告此技能的问题